Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45456
    Prev
    Next
    INDEX
    Explanations

    personal experiences and stories shared by individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    1.4%
    718
    +0.10
    0.6%
    307
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.24
    0.18
    718
    +0.10
    0.20
    502
    +0.09
    0.13
    Negative Logits
    Owner
    -0.51
    Downloadha
    -0.50
    INGTON
    -0.50
    icons
    -0.47
    etry
    -0.46
     Ezekiel
    -0.45
    heres
    -0.45
    etric
    -0.45
     2048
    -0.44
     chloride
    -0.44
    POSITIVE LOGITS
    ñ
    0.63
     suppose
    0.60
    arag
    0.60
    AU
    0.58
     interviewed
    0.57
    'm
    0.55
     guess
    0.55
     presume
    0.55
    cade
    0.52
     glimpse
    0.52
    Activations Density 11.312%

    No Known Activations